An Evolutionary Neural Learning Algorithm for Offline Cursive Handwriting Words with Hamming Network Lexicon

Original Word Image Rule Based Segmentation Character Resizing Recognition of Character using an ANN (trained with EALTS-BT) Lexicon Analyser Input Feature Extraction Output In this paper we incorporate a hybrid evolutionary method, which uses a combination of genetic algorithm and matrix based solution method such as QR factorization. A heuristic segmentation algorithm is initially used to over segment each word. Then the segmentation points are passed through the rule-based module to discard the incorrect segmentation points and include any missing segmentation points. Following the segmentation the connected contour is extracted between two correct segmentation points. The contour is passed through the feature extraction module that extracts the angular features of the contour, after which the EALS-BT algorithm finds the architecture and the weights for the classifier network. These recognized characters are grouped into words and passed to a variable length lexicon that retrieves words that has highest confidence value. Hamming neural network is used as a lexicon that rectifies the word misrecognized by the classifier. We have used CEDAR benchmark dataset and UCI Machine Learning repository (Upper case) to test the train and test the system